Skip to main content
Glama
cturkieh

France Data MCP

rpps_search_by_name

Read-onlyIdempotent

Search for healthcare professionals by last name using fuzzy trigram matching tolerant to accents and typos. Optionally refine by first name and department to find specific practitioners.

Instructions

Recherche fuzzy de professionnels de santé par identité (nom + prénom optionnel + département optionnel). Utilise un matching trigram (pg_trgm) tolérant aux accents, typos et variations d'orthographe. Tri par pertinence décroissante. Source : RPPS / Annuaire Santé ANS (Supabase dump mensuel).

Usage typique : "trouve-moi le Dr Martin à Paris" (nom obligatoire, prénom et département facultatifs pour affiner). Sans département, recherche nationale (peut renvoyer beaucoup d'homonymes — utiliser le match_score pour trier).

Format de retour : objet { count, truncated, results, query_metadata } aligné sur les autres tools RPPS de listing. Chaque résultat porte un champ match_score ∈ [0..1] (score trigram pg_trgm). Un score < 0.5 indique souvent une homonymie partielle à confirmer côté caller.

Par défaut, ne renvoie que les PS de catégorie Civil (C) — droit privé : libéraux, salariés privés, hospitaliers contractuels, ~97 % de la base. Passer include_agents_publics: true pour inclure aussi les Agents publics (M) — fonctionnaires d'État + collectivités + militaires SSA, ~0,3 % (PH titulaires, médecins inspecteurs ARS, médecins conseils CNAM, médecins scolaires Éducation nationale, médecins PMI). Passer include_etudiants: true pour inclure aussi les Étudiants (E) — internes, externes, élèves IDE/SF, ~2,5 %. Source nomenclature : https://mos.esante.gouv.fr/NOS/TRE_R09-CategorieProfessionnelle/.

Source : Annuaire Santé, Agence du Numérique en Santé (ANS) — Licence Ouverte v2.0

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nomYesNom de famille (obligatoire, non vide).
prenomNoPrénom (optionnel — affine le score si fourni).
departementNoCode département INSEE (ex: '75', '2A', '2B', '971'). Métropole 2 caractères (Corse '2A'/'2B', pas '20'), DOM/COM 3 caractères. Optionnel.
include_etudiantsNo
include_agents_publicsNo
limitNoNombre max de résultats (1-500, défaut 100).
include_freshnessNoSi true, ajoute un champ `data_freshness` au payload (dans `query_metadata` si présent, sinon à la racine) listant la dernière ingestion réussie par source (FINESS, Ameli, RPPS) avec `staleness_days`. Opt-in pour ne pas alourdir les payloads par défaut. Cache 5min côté serveur — coût négligeable.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesNombre d'entrées retournées dans `results` (post-troncature).
truncatedNotrue si le total réel dépasse `limit` (re-paginer via `offset` si supporté). Optional sur les tools de listing exhaustif (lister_*).
resultsYesEntrées métier (shape spécifique au tool, cf. description du tool).
query_metadataNoMetadata de la query (radius_km, departement, filtres appliqués, …).
freshnessNoFraîcheur des sources (présent si `include_freshness: true`).
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds extensive behavior beyond annotations: describes trigram matching tolerance, sorting by relevance, match_score interpretation (<0.5 indicates partial homonymy), default category filtering (Civil only with ~97% coverage), and data source update frequency. No contradictions with readOnlyHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Although lengthy, the description is well-structured: starts with core purpose, then typical usage, output format, default filters, and optional parameters. Every section adds value, and the information density is high without repetition. Appropriate for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Comprehensive coverage of purpose, parameters, behavior (matching algorithm, sorting, default filtering), output format (count, truncated, results, query_metadata), source and license, freshness tracking, and usage tips. No major gaps remain for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds substantial meaning beyond the schema: explains roles of nom, prenom, departement in matching, clarifies optional parameters include_agents_publics and include_etudiants with statistics and examples, defines limit defaults, and details include_freshness behavior. Schema coverage is 71%, but description compensates fully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool performs fuzzy search of health professionals by identity (nom, prenom, departement) using trigram matching. It distinguishes itself from sibling tools like professionnel_by_rpps (by RPPS ID) and others, specifying unique fuzzy name search capability.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use guidance with a typical example, warns about nationwide search leading to many homonyms, advises using match_score for sorting, and explains optional parameters for filtering categories. Though it does not explicitly list alternative tools, the usage context is thorough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cturkieh/france-data-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server